pi-ollama-cloud 0.5.0 → 0.7.0

package/CHANGELOG.md

@@ -2,6 +2,24 @@
 
 All notable changes to this project will be documented in this file.
 
+## [Unreleased]
+
+- Fix extension crash on pi 0.80.8+ where `AuthStorage` is no longer exported by `@earendil-works/pi-coding-agent`. Web tools now resolve the API key through the tool execution context's `modelRegistry.getApiKeyForProvider()`, preserving runtime/CLI overrides and the registered `apiKey: "$OLLAMA_API_KEY"` config. Thanks @badlogic for the cross-version analysis (#34, #35, #37).
+- Restore the `OLLAMA_API_KEY` env-var fallback in `ollama_web_search` and `ollama_web_fetch`. Thanks @cawilliamson (#26).
+- Add a 15s timeout to web search/fetch requests and preserve tool-cancellation by extending `fetchJsonWithTimeout` with an external `AbortSignal`.
+- Always target `https://ollama.com` and warn when `OLLAMA_API_BASE` is set to a non-cloud host, instead of silently querying a local Ollama daemon. Thanks @valueforvalue (#32, #33).
+- Add a `glm-5.2` thinking level map exposing `off`, `high`, and `xhigh` (`reasoning_effort: "none"`, `"high"`, `"max"`). Thanks @Thinkscape (#29).
+- Add estimated per-token pricing for Ollama Cloud models so `/cost` shows comparable usage. Prices are generated from [models.dev](https://models.dev) (the same source pi uses) via `scripts/generate-pricing.ts` into `pricing.generated.ts`, not hand-typed, and regenerate with the catalog via `npm run generate-models`. Prices are pinned to the installed package version: `/ollama-cloud-refresh` updates the model list and metadata but does not re-fetch prices, so newly added models register with zero cost until the next release. Not actual subscription charges. Thanks @DxTa (#9).
+- Refresh the generated model catalog from the live Ollama Cloud API. Adds `glm-5.2` (1M context, text-only) and `kimi-k2.7-code` (262K context, text + image). `deepseek-v4-pro` context window is now 524288 (was 1048576).
+- Retire models deprecated per https://docs.ollama.com/cloud#deprecations: July 15, 2026 batch (`deepseek-v3.1:671b`, `deepseek-v3.2`, `devstral-2:123b`, `devstral-small-2:24b`, `ministral-3:14b`, `ministral-3:3b`, `ministral-3:8b`, `gemini-3-flash-preview`, `gemma3:12b`, `gemma3:27b`, `gemma3:4b`, `glm-4.7`, `glm-5`, `minimax-m2.1`, `qwen3-coder-next`, `qwen3-coder:480b`) and June 30 (`rnj-1:8b`). The shipped catalog goes from 30 to 18 models.
+- Bump `@earendil-works/pi-coding-agent` runtime dependency to 0.80.10.
+
+## [0.6.0] - 2026-06-05
+
+- Fix `apiKey` registered as a literal string instead of an environment variable reference. Changed `apiKey: "OLLAMA_API_KEY"` to `apiKey: "$OLLAMA_API_KEY"` in `registerProvider`, resolving the deprecation warning emitted by pi v0.77.0+ and making the `OLLAMA_API_KEY` env var work alongside `auth.json` (env var takes priority, falls back to `auth.json`). Thanks @mandusm (#21).
+- Make `scripts/generate-models.ts` produce a stable output: sort models by `id` and each object's keys alphabetically (with `id` and `name` first), so regenerating the catalog produces minimal diffs. Thanks @shyim for the idea (#22).
+- Exclude models announced for retirement (effective 2026-06-16) from the generated `GENERATED_MODELS` list: `kimi-k2-thinking`, `kimi-k2:1t`, `minimax-m2`, `glm-4.6`, `qwen3-next:80b`, `qwen3-vl:235b`, `qwen3-vl:235b-instruct`, `cogito-2.1:671b`. See https://docs.ollama.com/cloud#deprecations. `/ollama-cloud-refresh` will still register them from the live API until Ollama removes them.
+
 ## [0.5.0] - 2026-05-22
 
 - Update `peerDependencies` and imports to the new `@earendil-works/*` packages.

package/README.md

@@ -1,6 +1,6 @@
 # pi-ollama-cloud
 
-Ollama Cloud provider plugin for [Pi](https://github.com/badlogic/pi-mono) coding agent.
+Ollama Cloud provider plugin for the [Pi](https://pi.dev) coding agent.
 
 Registers Ollama Cloud as a model provider with dynamically fetched models, and provides `ollama_web_search` and `ollama_web_fetch` tools that use the [Ollama Cloud web search API](https://docs.ollama.com/capabilities/web-search) - no local Ollama server required.
 
@@ -14,7 +14,7 @@ Registers Ollama Cloud as a model provider with dynamically fetched models, and
 - **`/ollama-cloud-refresh` command** - Re-fetches the model list and updates the cache and provider registration live (no restart needed).
 - **`ollama_web_search` tool** - Search the web for real-time information using Ollama Cloud's `/api/web_search` endpoint. Returns titles, URLs, and content snippets.
 - **`ollama_web_fetch` tool** - Fetch and extract text content from a web page URL using Ollama Cloud's `/api/web_fetch` endpoint. Returns page title, content, and links.
-- **Zero cost tracking** - All models are registered with zero costs since Ollama Cloud uses a flat subscription model (Free, Pro, Max) rather than per-token billing. Per-request costs don't apply, so Pi's cost tracker always shows zero. See [ollama.com/pricing](https://ollama.com/pricing) for plan details.
+- **Estimated cost tracking** - Models are registered with estimated per-token costs sourced from [models.dev](https://models.dev) (the same catalog pi uses), so Pi's `/cost` shows comparable usage. Ollama Cloud is subscription-billed (Free, Pro, Max), so these are equivalent pay-as-you-go estimates, not actual charges. See [ollama.com/pricing](https://ollama.com/pricing) for plan details.
 
 ## Prerequisites
 
@@ -142,11 +142,11 @@ Model metadata is derived from the cached data:
 | Field | Source |
 |---|---|
 | `reasoning` | `capabilities` includes `"thinking"` |
-| `thinkingLevelMap` | [`thinking-levels.ts`](thinking-levels.ts) with 4 maps (DEFAULT, GPT_OSS, QWEN3, NO_OFF) based on API testing |
+| `thinkingLevelMap` | [`thinking-levels.ts`](thinking-levels.ts) with 5 maps (DEFAULT, GPT_OSS, QWEN3, GLM_52, NO_OFF) based on API testing |
 | `input` | `["text", "image"]` if `capabilities` includes `"vision"`, else `["text"]` |
 | `contextWindow` | `model_info.*.context_length` (falls back to 128000) |
 | `maxTokens` | Fixed at 32768 |
-| `cost` | All zeros (Ollama Cloud uses subscription plans, not per-token billing - see [pricing](https://ollama.com/pricing)) |
+| `cost` | Estimated per-1M-token prices from [models.dev](https://models.dev), generated by `scripts/generate-pricing.ts` into `pricing.generated.ts`. Ollama Cloud is subscription-billed, so these are equivalent pay-as-you-go estimates, not actual charges. Unmapped models default to zero. Prices are pinned to the installed package version: `/ollama-cloud-refresh` updates the model list and metadata but does not re-fetch prices, so newly added models register with zero cost until the next release. |
 
 ### Thinking level mapping
 
@@ -157,6 +157,7 @@ Pi's thinking levels are mapped to Ollama Cloud's OpenAI-compatible `reasoning_e
 | `DEFAULT` | Most thinking models | off, low, medium, high, xhigh | `minimal` hidden (duplicate of low) |
 | `GPT_OSS` | `gpt-oss*` | low, medium, high | Can't disable thinking, no off or xhigh |
 | `QWEN3` | `qwen3*` (except `qwen3-vl*`) | off, medium | Binary-only (think/nothink), no gradation |
+| `GLM_52` | `glm-5.2` | off, high, xhigh | GLM supports disabled thinking; Ollama's model page confirms `high` and `max` reasoning efforts |
 | `NO_OFF` | `qwen3-vl*`, `kimi-k2-thinking`, `minimax*` | low, medium, high, xhigh | "none" doesn't disable thinking on these models |
 
 See [docs/think-experiment.md](docs/think-experiment.md) for the testing methodology and results.
@@ -182,7 +183,7 @@ Both tools use the same Ollama Cloud API key configured for the provider. No loc
 
 | Command | Description |
 |---|---|
-| `/ollama-cloud-refresh` | Fetch models from the Ollama Cloud API, update cache, and re-register the provider |
+| `/ollama-cloud-refresh` | Fetch models from the Ollama Cloud API, update cache, and re-register the provider. Updates the model list and metadata but not estimated prices (those are pinned to the installed package version). |
 | `/ollama-webtools [on\|off\|enable\|disable]` | Enable or disable the `ollama_web_search` and `ollama_web_fetch` tools. Toggles if no argument given. |
 
 ## Development

package/index.ts

@@ -46,7 +46,7 @@ function registerProvider(pi: ExtensionAPI, models: ProviderModelConfig[]) {
   pi.registerProvider("ollama-cloud", {
     name: "Ollama Cloud",
     baseUrl: `${OLLAMA_BASE}/v1`,
-    apiKey: "OLLAMA_API_KEY",
+    apiKey: "$OLLAMA_API_KEY",
     api: "openai-completions",
     models,
   });
@@ -124,9 +124,8 @@ export default async function (pi: ExtensionAPI) {
   // When cache is missing, GENERATED_MODELS serves as the cache —
   // it is manually generated via `npm run generate-models` and committed to the repo.
   const needsStartupRefresh = cacheState.status === "stale";
-  // GENERATED_MODELS ships with the package (36 tool-capable models from
-  // the build script). Used when no local cache exists. A fresh user cache
-  // from /ollama-cloud-refresh takes precedence over the generated list.
+  // GENERATED_MODELS ships with the package. Used when no local cache exists. A
+  // fresh user cache from /ollama-cloud-refresh takes precedence over the generated list.
   const models = cacheState.status === "missing" ? GENERATED_MODELS : assembleModels(cacheState.models);
 
   registerProvider(pi, models);